How I can create a custom dataset on PyTorch geometric (PyG) with multiple graphs from a Pandas DataFrame, where each row represents a graph and the columns their features.
I want to use this dataset to train a GAT to do a graph classification task.
How I can create a custom dataset on PyTorch geometric (PyG) with multiple graphs from a Pandas DataFrame, where each row represents a graph and the columns their features.
I want to use this dataset to train a GAT to do a graph classification task.